Search

Your search keyword '"Ren, Qingyang"' showing total 166 results
Start Over Author "Ren, Qingyang"
166 results on '"Ren, Qingyang"'

1. A survey on fairness of large language models in e-commerce: progress, application, and challenge

Author

Ren, Qingyang, Jiang, Zilin, Cao, Jinghan, Li, Sijia, Li, Chiqu, Liu, Yiyang, Huo, Shuning, He, Tiange, and Chen, Yuan

Subjects
Computer Science - Computation and Language, Computer Science - Artificial Intelligence, Computer Science - Computers and Society
Abstract

This survey explores the fairness of large language models (LLMs) in e-commerce, examining their progress, applications, and the challenges they face. LLMs have become pivotal in the e-commerce domain, offering innovative solutions and enhancing customer experiences. This work presents a comprehensive survey on the applications and challenges of LLMs in e-commerce. The paper begins by introducing the key principles underlying the use of LLMs in e-commerce, detailing the processes of pretraining, fine-tuning, and prompting that tailor these models to specific needs. It then explores the varied applications of LLMs in e-commerce, including product reviews, where they synthesize and analyze customer feedback; product recommendations, where they leverage consumer data to suggest relevant items; product information translation, enhancing global accessibility; and product question and answer sections, where they automate customer support. The paper critically addresses the fairness challenges in e-commerce, highlighting how biases in training data and algorithms can lead to unfair outcomes, such as reinforcing stereotypes or discriminating against certain groups. These issues not only undermine consumer trust, but also raise ethical and legal concerns. Finally, the work outlines future research directions, emphasizing the need for more equitable and transparent LLMs in e-commerce. It advocates for ongoing efforts to mitigate biases and improve the fairness of these systems, ensuring they serve diverse global markets effectively and ethically. Through this comprehensive analysis, the survey provides a holistic view of the current landscape of LLMs in e-commerce, offering insights into their potential and limitations, and guiding future endeavors in creating fairer and more inclusive e-commerce environments., Comment: 21 pages, 9 figures

Published
2024

2. Off-Policy Evaluation for Large Action Spaces via Conjunct Effect Modeling

Author

Saito, Yuta, Ren, Qingyang, and Joachims, Thorsten

Subjects
Statistics - Machine Learning, Computer Science - Artificial Intelligence, Computer Science - Machine Learning
Abstract

We study off-policy evaluation (OPE) of contextual bandit policies for large discrete action spaces where conventional importance-weighting approaches suffer from excessive variance. To circumvent this variance issue, we propose a new estimator, called OffCEM, that is based on the conjunct effect model (CEM), a novel decomposition of the causal effect into a cluster effect and a residual effect. OffCEM applies importance weighting only to action clusters and addresses the residual causal effect through model-based reward estimation. We show that the proposed estimator is unbiased under a new condition, called local correctness, which only requires that the residual-effect model preserves the relative expected reward differences of the actions within each cluster. To best leverage the CEM and local correctness, we also propose a new two-step procedure for performing model-based estimation that minimizes bias in the first step and variance in the second step. We find that the resulting OffCEM estimator substantially improves bias and variance compared to a range of conventional estimators. Experiments demonstrate that OffCEM provides substantial improvements in OPE especially in the presence of many actions., Comment: accepted at ICML2023. arXiv admin note: text overlap with arXiv:2202.06317

Published
2023

28. Macroscopic and Mesoscopic Damage Characteristics and Energy Evolution Laws of Rock Mass With Double Arcuate Fractures Under Uniaxial Compression.

Author

Ren, Qingyang, Gao, Senlin, Xiao, Songqiang, Meng, Xin, and Li, Zhongyao

Abstract

ABSTRACT In order to reveal the influence of double arc‐shaped fissure dip angles on the macro‐micro failure and energy evolution laws of rock masses, a numerical model of red sandstone was firstly established using the PFC2D. Moreover, mesoscopic parameters of the numerical model were calibrated based on the uniaxial compression tests on intact and single straight fissure red sandstone specimens. Then, particle flow simulation tests of red sandstone with different arc‐shaped fissure dip angles were carried out. The results show that the peak strength and elastic modulus both increase with the increase of arc‐shaped fissure dip angle α, exhibiting an oblique shear‐tensile failure pattern. Six types of cracks evolved during the instability and rupture of the rock mass with double arc‐shaped fissures. The macroscopic fissures in the rock mass ultimately penetrate along the extension direction of the arc‐shaped fissures. As the arc‐shaped fissure dip angle α increases, the crack evolution is positively correlated with the acoustic emission (AE) of the specimen. When approaching instability failure, the AE ringing count rapidly increases. There is a critical angle limit inflection point for the total energy absorbed by the rock between 60° and 75°, with a total energy increase of about 54%. During instability failure, it is dominated by dissipative energy, with elastic energy as a supplement. This article derived a damage constitutive model of red sandstone with different arc‐shaped fissure dip angles, revealing the damage laws of red sandstone under different arc‐shaped fissure dip angles. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

42. Research on calculation model for ultimate bearing capacity of tensile type anchor cables and the shape of internal fracture surface in anchorage segment.

Author

Ren, Qingyang, Meng, Xin, Chen, Bin, Xiao, Songqiang, Jin, Honghua, Mou, Shan, and Li, Zhongyao

Subjects
*ANCHORS, *ANCHORAGE, *CABLES, *SHEAR strength
Abstract

The generalized model and parameter equation for the internal fracture surface of tensile type anchor cable anchorage section are constructed, and the calculation model of ultimate bearing capacity is derived based on the principle of limit equilibrium. The shape of the internal fracture surface in the anchorage section and the expression of its parameter equation are experimentally studied, and the variation law of the parameter equation and fracture range with the diameter of the anchor cable and confining pressure is analyzed. The parameter equation is substituted into the calculation model to realize the calculation and verification of the model. Through theoretical derivation, a calculation model of ultimate bearing capacity of anchor cable is obtained, which comprehensively considers the average shear strength of anchorage section, the shape of fracture surface, fracture range and confining pressure. The tests show that according to the magnitude of the confining pressure on the anchorage section, the internal fracture surface takes on two shapes: cylindrical and trumpet‐shaped, the parameter equation of trumpet‐shaped fracture surface obeys logarithmic distribution approximately. The coefficient a decreases with the increase of confining pressure but increases with the increase of anchor cable diameter, the constant b increases with the increase of confining pressure but decreases with the increase of anchor cable diameter. The ranges of horizontal and vertical fracture decrease with the increase of confining pressure, and increase with the increase of anchor cable diameter. The deviations between the theoretical calculation and the experimental results are less than 6.5%. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

47. Field test of blasting vibration and adjacent slope stability under the influence of blasting vibration in mining

Author

Liu, Can, Wang, Feifei, Ren, Qingyang, Chen, Bin, Jin, Honghua, Cui, Songjun, Zhu, Ziqiang, Liu, Can, Wang, Feifei, Ren, Qingyang, Chen, Bin, Jin, Honghua, Cui, Songjun, and Zhu, Ziqiang

Abstract

Blasting mining in open-pit has a significant impact on the adjacent slope, which often causes the rock mass cracking and spalling of the slope to form a landslide disaster. In order to explore the impact of blasting vibration on the adjacent slope, field tests were carried out with professional testing equipment, and several blasting vibration data were measured. Sadovsky formula was used for fitting analysis, and the influence coefficient of blasting vibration was obtained. The slope stability analysis was carried out by using the limit equilibrium SLIDE analysis software, and the slope safety factor under the influence of blasting vibration was obtained. The results show that: The maximum blasting vibration speed monitored in this blasting is 2.1987 cm/s, and the main vibration frequency is 14.6484 Hz. Therefore, according to the standards in the regulations, the impact of this blasting on the slope meets the corresponding requirements. In this slope stability analysis, the blasting vibration influence coefficient Kc= 0.032, when 40 m away from the final slope is used. Morgen Prince method and Spencer method generally have higher safety factors than Bishop method. The safety factor of the analysis section at the 45° slope angle is 1.217. The slope can maintain stability under the influence of blasting vibration.

Published
2023

Catalog

Books, media, physical & digital resources
See catalog results